examples/jobs/skills-merge/skills/runtime-proof/SKILL.md
Write the proof file for the Harbor runtime skill injection example.
npx skillsauth add laude-institute/harbor runtime-proofInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Write exactly this text to /app/skill-proof.txt:
runtime skill injected successfully
testing
Write Harbor task verifiers using Reward Kit. Use when creating or editing a task's tests/ directory, adding grading criteria, setting up LLM/agent judges, or designing verifiers that produce a reward score.
development
Create a new Harbor task for evaluating agents. Use when the user wants to scaffold, build, or design a new task, benchmark problem, or eval. Guides through instruction writing, environment setup, verifier design (pytest vs Reward Kit vs custom), and solution scripting.
data-ai
Existing task skill that should remain after job-level skill injection.
data-ai
Publish a Harbor task or dataset to the registry. Use when the user wants to upload, publish, or share tasks or datasets/benchmarks on the Harbor registry.